Zero-Shot Temporal Action Localization Through Textual Guidance
Benedetta Liberatori, Alessandro Conti, Lorenzo Vaquero, Paolo Rota, Yiming Wang, Elisa Ricci. Face and Gestures 2026.
Paolo Rota
Associate Professor @ Department of Psichology and Cognitive Science - University of Trento
Piazza Manifattura 1, edificio 14, - Room 150 - 38068 Rovereto (TN)
Polo Ferrari - Via Sommarive , 9 - Room 110 - (Povo 2) - I-38123 Povo (TN)
Ongoing I am part of the MHUG group of the University of Trento. If you are interested in working or visiting the MHUG group, please fill this form.
About me
I am Paolo Rota, associate professor at the University of Trento and ELLIS member, working in computer vision, machine learning, and multimodal AI. My research focuses on vision-language models and activity recognition, with applications in video analytics and industrial AI.
My research focuses on computer vision and machine learning, with a particular emphasis on video understanding and multimodal AI. I investigate methods that bridge vision and language, addressing challenges such as zero-shot action recognition, temporal action localization, and open-world recognition using large vision–language models. More broadly, I work on representation learning and domain adaptation to build systems capable of robust visual understanding in dynamic and real-world environments. I am also interested in evaluation protocols and benchmark design for video analytics, aiming to develop principled and reliable ways to assess multimodal AI systems.
Outside of academia, I co-founded Mountain Maps, a startup that uses AI to enhance outdoor navigation and help people explore mountain environments more safely and enjoyably.
News
My talk, Foundation Models Beyond Domain Boundaries, closed the week in the session on AI methods, alongside Silvia Storti (University of Verona) and Giulia Lioi (IMT Atlantique). Nice to bring a computer vision and big models perspective to a room of neurophysiologists, and the local programme on open science and TMS-EEG was worth the trip in itself.
Benedetta's paper Video-Language Entailment for Video Similarity Estimation has been accepted at EMNLP 2026 Findings!
We look at video differencing in the setting models are actually trained for: instead of concatenating two videos to spot what changed, we ask whether the caption of one video is entailed by the other.
The preprint will be on arXiv soon.
Congrats Bene!!
Group Members
PhD Students
Benedetta Liberatori
Co-advised with Elisa Ricci
Vision and Language
Video Understanding
Video Differencing
Anomaly Detection
Jiaqi Liu
Co-advised with Nicu Sebe
Image Generation
Pose Transfer
Video Generation
WAM
Yan Shu
Co-advised with Nicu Sebe
Remote Sensing
Vision and Language
Temporal Modelling
Video Understanding
Ester Riccardi
Co-advised with Roberto Bottini
Biological-inspired Media Generation
Brain decoding
Former Students
Alessandro Conti
Giacomo Zara
Recent Publications
TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation
Yan Shu, Bin Ren, Zhitong Xiong, Xiao Xiang Zhu, Begüm Demir, Nicu Sebe, Paolo Rota. CVPR 2026.
Rank-based Geographical Regularization: Revisiting Contrastive Self-Supervised Learning for Multispectral Remote Sensing Imagery
Tom Burgert, Leonard Hackel, Paolo Rota, Begüm Demir. WACV 2026.
Vocabulary-free Image Classification and Semantic Segmentation
Alessandro Conti, Enrico Fini, Massimiliano Mancini, Paolo Rota, Yiming Wang, Elisa Ricci. T-PAMI 2026.
Dense Motion Captioning
Shiyao Xu, Benedetta Liberatori, Gül Varol, Paolo Rota. 3DV 2026.
ConViS-Bench: Estimating Video Similarity Through Semantic Concepts
Benedetta Liberatori, Alessandro Conti, Lorenzo Vaquero, Yiming Wang, Elisa Ricci, Paolo Rota. NeurIPS 2025.
ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression
Tom Burgert, Oliver Stoll, Paolo Rota, Begüm Demir. NeurIPS (Oral) 2025.
On Large Multimodal Models as Open-World Image Classifiers
Alessandro Conti, Massimiliano Mancini, Enrico Fini, Yiming Wang, Paolo Rota, Elisa Ricci. ICCV 2025.
Automatic benchmarking of large multimodal models via iterative experiment programming
Alessandro Conti, Enrico Fini, Paolo Rota, Yiming Wang, Massimiliano Mancini, Elisa Ricci. ICIAP 2025.
Multi-focal Conditioned Latent Diffusion for Person Image Synthesis
Jiaqi Liu, Jichao Zhang, Paolo Rota, Nicu Sebe. CVPR 2025.
Simplifying Open-Set Video Domain Adaptation with Contrastive Learning
Giacomo Zara, Victor Guilherme Turrisi da Costa, Subhankar Roy, Paolo Rota, Elisa Ricci. CVIU 2024.
Text-Enhanced Zero-Shot Action Recognition: A Training-Free Approach
Massimo Bosetti, Shibingfeng Zhang, Benedetta Liberatori, Giacomo Zara, Elisa Ricci, Paolo Rota. ICPR 2024.
Test-time zero-shot temporal action localization
Benedetta Liberatori, Alessandro Conti, Paolo Rota, Yiming Wang, Elisa Ricci. CVPR 2024.
AutoLabel: CLIP-based framework for open-set video domain adaptation
Giacomo Zara, Subhankar Roy, Paolo Rota, Elisa Ricci. CVPR 2023.
The unreasonable effectiveness of large language-vision models for source-free video domain adaptation
Giacomo Zara, Alessandro Conti, Subhankar Roy, Stéphane Lathuilière, Paolo Rota, Elisa Ricci. ICCV 2023.
Vocabulary-free image classification
Alessandro Conti, Enrico Fini, Massimiliano Mancini, Paolo Rota, Yiming Wang, Elisa Ricci. NeurIPS 2023.